The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the otelcol-contrib binary to validate and verify configuration splits.
Evidence: references/verifying.md contains specific instructions to run otelcol-contrib validate and otelcol-contrib print-config to ensure behavior equivalence.
[PROMPT_INJECTION]: The skill processes user-supplied OpenTelemetry configuration files, which constitutes a surface for indirect prompt injection if the files contain malicious content that influences the agent's logic or CLI tool behavior.
Ingestion points: Monolithic OTel collector configuration files provided by the user (as described in SKILL.md).
Boundary markers: Not present; the skill lacks explicit instructions to treat the configuration data as untrusted or to use delimiters to prevent command injection or instruction override.
Capability inventory: The skill facilitates file writing and subprocess execution (otelcol-contrib).
Sanitization: Absent; there are no instructions to sanitize or validate the content of the YAML files beyond checking structural equivalence.

ollygarden-otel-collector-config-decomposition